include beta metrics in documentation and update docs for metrics

test/instrumentation/documentation/documentation-list.yaml

@@ -270,17 +270,6 @@
   - 128
   - 256
   - 512
-- name: attachdetach_controller_forced_detaches
-  help: Number of times the A/D Controller performed a forced detach
-  type: Counter
-  stabilityLevel: ALPHA
-- name: attachdetach_controller_total_volumes
-  help: Number of volumes in A/D Controller
-  type: Custom
-  stabilityLevel: ALPHA
-  labels:
-  - plugin_name
-  - state
 - name: pod_failures_handled_by_failure_policy_total
   subsystem: job_controller
   help: "`The number of failed Pods handled by failure policy with\n\t\t\trespect
@@ -317,6 +306,34 @@
   stabilityLevel: ALPHA
   labels:
   - zone
+- name: update_all_nodes_health_duration_seconds
+  subsystem: node_collector
+  help: Duration in seconds for NodeController to update the health of all nodes.
+  type: Histogram
+  stabilityLevel: ALPHA
+  buckets:
+  - 0.01
+  - 0.04
+  - 0.16
+  - 0.64
+  - 2.56
+  - 10.24
+  - 40.96
+  - 163.84
+- name: update_node_health_duration_seconds
+  subsystem: node_collector
+  help: Duration in seconds for NodeController to update the health of a single node.
+  type: Histogram
+  stabilityLevel: ALPHA
+  buckets:
+  - 0.001
+  - 0.004
+  - 0.016
+  - 0.064
+  - 0.256
+  - 1.024
+  - 4.096
+  - 16.384
 - name: zone_health
   subsystem: node_collector
   help: Gauge measuring percentage of healthy nodes per zone.
@@ -365,6 +382,13 @@
   stabilityLevel: ALPHA
   labels:
   - clusterCIDR
+- name: cirdset_max_cidrs
+  subsystem: node_ipam_controller
+  help: Maximum number of CIDRs that can be allocated.
+  type: Gauge
+  stabilityLevel: ALPHA
+  labels:
+  - clusterCIDR
 - name: multicidrset_allocation_tries_per_request
   subsystem: node_ipam_controller
   help: Histogram measuring CIDR allocation tries per request.
@@ -399,6 +423,13 @@
   stabilityLevel: ALPHA
   labels:
   - clusterCIDR
+- name: multicirdset_max_cidrs
+  subsystem: node_ipam_controller
+  help: Maximum number of CIDRs that can be allocated.
+  type: Gauge
+  stabilityLevel: ALPHA
+  labels:
+  - clusterCIDR
 - name: force_delete_pod_errors_total
   subsystem: pod_gc_collector
   help: Number of errors encountered when forcefully deleting the pods since the Pod
@@ -427,13 +458,16 @@
   - 2
   - 4
   - 8
-- name: storage_count_attachable_volumes_in_use
+- name: create_attempts_total
-  help: Measure number of volumes in use
+  subsystem: resourceclaim_controller
-  type: Custom
+  help: Number of ResourceClaims creation requests
+  type: Counter
+  stabilityLevel: ALPHA
+- name: create_failures_total
+  subsystem: resourceclaim_controller
+  help: Number of ResourceClaims creation request failures
+  type: Counter
   stabilityLevel: ALPHA
-  labels:
-  - node
-  - volume_plugin
 - name: job_deletion_duration_seconds
   subsystem: ttl_after_finished_controller
   help: The time it took to delete the job since it became eligible for deletion
@@ -513,6 +547,17 @@
   stabilityLevel: STABLE
   labels:
   - zone
+- name: attachdetach_controller_forced_detaches
+  help: Number of times the A/D Controller performed a forced detach
+  type: Counter
+  stabilityLevel: ALPHA
+- name: attachdetach_controller_total_volumes
+  help: Number of volumes in A/D Controller
+  type: Custom
+  stabilityLevel: ALPHA
+  labels:
+  - plugin_name
+  - state
 - name: create_failures_total
   subsystem: ephemeral_volume_controller
   help: Number of PersistenVolumeClaims creation requests
@@ -625,6 +670,13 @@
     claim
   type: Counter
   stabilityLevel: ALPHA
+- name: storage_count_attachable_volumes_in_use
+  help: Measure number of volumes in use
+  type: Custom
+  stabilityLevel: ALPHA
+  labels:
+  - node
+  - volume_plugin
 - name: volume_operation_total_errors
   help: Total volume operation errors
   type: Counter
@@ -1104,6 +1156,37 @@
   help: Cumulative number of pods started
   type: Counter
   stabilityLevel: ALPHA
+- name: topology_manager_admission_duration_ms
+  subsystem: kubelet
+  help: Duration in milliseconds to serve a pod admission request.
+  type: Histogram
+  stabilityLevel: ALPHA
+  buckets:
+  - 0.05
+  - 0.1
+  - 0.2
+  - 0.4
+  - 0.8
+  - 1.6
+  - 3.2
+  - 6.4
+  - 12.8
+  - 25.6
+  - 51.2
+  - 102.4
+  - 204.8
+  - 409.6
+  - 819.2
+- name: topology_manager_admission_errors_total
+  subsystem: kubelet
+  help: The number of admission request failures where resources could not be aligned.
+  type: Counter
+  stabilityLevel: ALPHA
+- name: topology_manager_admission_requests_total
+  subsystem: kubelet
+  help: The number of admission requests where resources have to be aligned.
+  type: Counter
+  stabilityLevel: ALPHA
 - name: kubelet_volume_stats_available_bytes
   help: Number of available bytes in the volume
   type: Custom
@@ -1183,29 +1266,6 @@
   labels:
   - pod
   - namespace
-- name: probe_duration_seconds
-  subsystem: prober
-  help: Duration in seconds for a probe response.
-  type: Histogram
-  stabilityLevel: ALPHA
-  labels:
-  - container
-  - namespace
-  - pod
-  - probe_type
-- name: probe_total
-  subsystem: prober
-  help: Cumulative number of a liveness, readiness or startup probe for a container
-    by result.
-  type: Counter
-  stabilityLevel: ALPHA
-  labels:
-  - container
-  - namespace
-  - pod
-  - pod_uid
-  - probe_type
-  - result
 - name: scrape_error
   help: 1 if there was an error while getting container metrics, 0 otherwise
   type: Custom
@@ -1432,6 +1492,29 @@
   help: Cumulative proxy rules Service changes
   type: Counter
   stabilityLevel: ALPHA
+- name: probe_duration_seconds
+  subsystem: prober
+  help: Duration in seconds for a probe response.
+  type: Histogram
+  stabilityLevel: ALPHA
+  labels:
+  - container
+  - namespace
+  - pod
+  - probe_type
+- name: probe_total
+  subsystem: prober
+  help: Cumulative number of a liveness, readiness or startup probe for a container
+    by result.
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - container
+  - namespace
+  - pod
+  - pod_uid
+  - probe_type
+  - result
 - name: volume_manager_selinux_container_errors_total
   help: Number of errors when kubelet cannot compute SELinux context for a container.
     Kubelet can't start such a Pod then and it will retry, therefore value of this
@@ -1534,6 +1617,34 @@
   stabilityLevel: ALPHA
   labels:
   - cidr
+- name: allocated_ports
+  subsystem: nodeport_allocator
+  namespace: kube_apiserver
+  help: Gauge measuring the number of allocated NodePorts for Services
+  type: Gauge
+  stabilityLevel: ALPHA
+- name: allocation_errors_total
+  subsystem: nodeport_allocator
+  namespace: kube_apiserver
+  help: Number of errors trying to allocate NodePort
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - scope
+- name: allocation_total
+  subsystem: nodeport_allocator
+  namespace: kube_apiserver
+  help: Number of NodePort allocations
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - scope
+- name: available_ports
+  subsystem: nodeport_allocator
+  namespace: kube_apiserver
+  help: Gauge measuring the number of available NodePorts for Services
+  type: Gauge
+  stabilityLevel: ALPHA
 - name: pods_logs_backend_tls_failure_total
   subsystem: pod_logs
   namespace: kube_apiserver
@@ -1550,34 +1661,6 @@
   stabilityLevel: ALPHA
   labels:
   - usage
-- name: kube_pod_resource_limit
-  help: Resources limit for workloads on the cluster, broken down by pod. This shows
-    the resource usage the scheduler and kubelet expect per pod for resources along
-    with the unit for the resource if any.
-  type: Custom
-  stabilityLevel: ALPHA
-  labels:
-  - namespace
-  - pod
-  - node
-  - scheduler
-  - priority
-  - resource
-  - unit
-- name: kube_pod_resource_request
-  help: Resources requested by workloads on the cluster, broken down by pod. This
-    shows the resource usage the scheduler and kubelet expect per pod for resources
-    along with the unit for the resource if any.
-  type: Custom
-  stabilityLevel: ALPHA
-  labels:
-  - namespace
-  - pod
-  - node
-  - scheduler
-  - priority
-  - resource
-  - unit
 - name: e2e_scheduling_duration_seconds
   subsystem: scheduler
   help: E2e scheduling latency in seconds (scheduling algorithm + binding). This metric
@@ -1740,6 +1823,34 @@
   help: Cumulative valid projected service account tokens used
   type: Counter
   stabilityLevel: ALPHA
+- name: kube_pod_resource_limit
+  help: Resources limit for workloads on the cluster, broken down by pod. This shows
+    the resource usage the scheduler and kubelet expect per pod for resources along
+    with the unit for the resource if any.
+  type: Custom
+  stabilityLevel: STABLE
+  labels:
+  - namespace
+  - pod
+  - node
+  - scheduler
+  - priority
+  - resource
+  - unit
+- name: kube_pod_resource_request
+  help: Resources requested by workloads on the cluster, broken down by pod. This
+    shows the resource usage the scheduler and kubelet expect per pod for resources
+    along with the unit for the resource if any.
+  type: Custom
+  stabilityLevel: STABLE
+  labels:
+  - namespace
+  - pod
+  - node
+  - scheduler
+  - priority
+  - resource
+  - unit
 - name: framework_extension_point_duration_seconds
   subsystem: scheduler
   help: Latency for running all plugins of a specific extension point.
@@ -2156,6 +2267,8 @@
   - 0.5
   - 1
   - 2.5
+  - 10
+  - 25
 - name: error_total
   subsystem: apiserver_audit
   help: Counter of audit events that failed to be audited properly. Plugin identifies
@@ -2184,11 +2297,13 @@
 - name: compilation_duration_seconds
   subsystem: cel
   namespace: apiserver
+  help: CEL compilation time in seconds.
   type: Histogram
   stabilityLevel: ALPHA
 - name: evaluation_duration_seconds
   subsystem: cel
   namespace: apiserver
+  help: CEL evaluation time in seconds.
   type: Histogram
   stabilityLevel: ALPHA
 - name: certificate_expiration_seconds
@@ -2553,12 +2668,10 @@
   labels:
   - status
 - name: field_validation_request_duration_seconds
-  help: Response latency distribution in seconds for each field validation value and
+  help: Response latency distribution in seconds for each field validation value
-    whether field validation is enabled or not
   type: Histogram
   stabilityLevel: ALPHA
   labels:
-  - enabled
   - field_validation
   buckets:
   - 0.05
@@ -2780,6 +2893,76 @@
   - 7680
   - 15360
   - 30720
+- name: invalid_key_id_from_status_total
+  subsystem: envelope_encryption
+  namespace: apiserver
+  help: Number of times an invalid keyID is returned by the Status RPC call split
+    by error.
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - error
+  - provider_name
+- name: key_id_hash_last_timestamp_seconds
+  subsystem: envelope_encryption
+  namespace: apiserver
+  help: The last time in seconds when a keyID was used.
+  type: Gauge
+  stabilityLevel: ALPHA
+  labels:
+  - key_id_hash
+  - provider_name
+  - transformation_type
+- name: key_id_hash_status_last_timestamp_seconds
+  subsystem: envelope_encryption
+  namespace: apiserver
+  help: The last time in seconds when a keyID was returned by the Status RPC call.
+  type: Gauge
+  stabilityLevel: ALPHA
+  labels:
+  - key_id_hash
+  - provider_name
+- name: key_id_hash_total
+  subsystem: envelope_encryption
+  namespace: apiserver
+  help: Number of times a keyID is used split by transformation type and provider.
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - key_id_hash
+  - provider_name
+  - transformation_type
+- name: kms_operations_latency_seconds
+  subsystem: envelope_encryption
+  namespace: apiserver
+  help: KMS operation duration with gRPC error code status total.
+  type: Histogram
+  stabilityLevel: ALPHA
+  labels:
+  - grpc_status_code
+  - method_name
+  - provider_name
+  buckets:
+  - 0.0001
+  - 0.0002
+  - 0.0004
+  - 0.0008
+  - 0.0016
+  - 0.0032
+  - 0.0064
+  - 0.0128
+  - 0.0256
+  - 0.0512
+  - 0.1024
+  - 0.2048
+  - 0.4096
+  - 0.8192
+  - 1.6384
+  - 3.2768
+  - 6.5536
+  - 13.1072
+  - 26.2144
+  - 52.4288
 - name: current_executing_requests
   subsystem: flowcontrol
   namespace: apiserver
@@ -3214,12 +3397,26 @@
   stabilityLevel: ALPHA
   labels:
   - endpoint
+- name: storage_decode_errors_total
+  namespace: apiserver
+  help: Number of stored object decode errors split by object type
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - resource
 - name: envelope_transformation_cache_misses_total
   subsystem: storage
   namespace: apiserver
   help: Total number of cache misses while accessing key decryption key(KEK).
   type: Counter
   stabilityLevel: ALPHA
+- name: storage_events_received_total
+  subsystem: apiserver
+  help: Number of etcd events received split by kind.
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - resource
 - name: apiserver_storage_list_evaluated_objects_total
   help: Number of objects tested in the course of serving a LIST request from storage
   type: Counter
@@ -3251,7 +3448,6 @@
   type: Histogram
   stabilityLevel: ALPHA
   labels:
-  - status
   - transformation_type
   - transformer_prefix
   buckets:
@@ -3305,6 +3501,14 @@
   stabilityLevel: ALPHA
   labels:
   - resource
+- name: events_received_total
+  subsystem: watch_cache
+  namespace: apiserver
+  help: Counter of events received in watch cache broken by resource type.
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - resource
 - name: initializations_total
   subsystem: watch_cache
   namespace: apiserver
@@ -3313,22 +3517,6 @@
   stabilityLevel: ALPHA
   labels:
   - resource
-- name: x509_insecure_sha1_total
-  subsystem: webhooks
-  namespace: apiserver
-  help: Counts the number of requests to servers with insecure SHA1 signatures in
-    their serving certificate OR the number of connection failures due to the insecure
-    SHA1 signatures (either/or, based on the runtime environment)
-  type: Counter
-  stabilityLevel: ALPHA
-- name: x509_missing_san_total
-  subsystem: webhooks
-  namespace: apiserver
-  help: Counts the number of requests to servers missing SAN extension in their serving
-    certificate OR the number of connection failures due to the lack of x509 certificate
-    SAN extension missing (either/or, based on the runtime environment)
-  type: Counter
-  stabilityLevel: ALPHA
 - name: etcd_bookmark_counts
   help: Number of etcd bookmarks (progress notify events) split by kind.
   type: Gauge
@@ -3405,6 +3593,22 @@
   stabilityLevel: STABLE
   labels:
   - resource
+- name: x509_insecure_sha1_total
+  subsystem: webhooks
+  namespace: apiserver
+  help: Counts the number of requests to servers with insecure SHA1 signatures in
+    their serving certificate OR the number of connection failures due to the insecure
+    SHA1 signatures (either/or, based on the runtime environment)
+  type: Counter
+  stabilityLevel: ALPHA
+- name: x509_missing_san_total
+  subsystem: webhooks
+  namespace: apiserver
+  help: Counts the number of requests to servers missing SAN extension in their serving
+    certificate OR the number of connection failures due to the lack of x509 certificate
+    SAN extension missing (either/or, based on the runtime environment)
+  type: Counter
+  stabilityLevel: ALPHA
 - name: nodesync_latency_seconds
   subsystem: service_controller
   help: A metric measuring the latency for nodesync which updates loadbalancer hosts
@@ -3572,6 +3776,14 @@
   - 15
   - 30
   - 60
+- name: rest_client_request_retries_total
+  help: Number of request retries, partitioned by status code, verb, and host.
+  type: Counter
+  stabilityLevel: ALPHA
+  labels:
+  - code
+  - host
+  - verb
 - name: rest_client_request_size_bytes
   help: Request size in bytes. Broken down by verb and host.
   type: Histogram
@@ -3850,6 +4062,12 @@
   - resource_group
   - source
   - subscription_id
+- name: number_of_l4_ilbs
+  help: Number of L4 ILBs
+  type: Gauge
+  stabilityLevel: ALPHA
+  labels:
+  - feature
 - name: cloudprovider_gce_api_request_duration_seconds
   help: Latency of a GCE API call
   type: Histogram
@@ -3908,12 +4126,6 @@
   help: Counter of failed Token() requests to the alternate token source
   type: Counter
   stabilityLevel: ALPHA
-- name: number_of_l4_ilbs
-  help: Number of L4 ILBs
-  type: Gauge
-  stabilityLevel: ALPHA
-  labels:
-  - feature
 - name: pod_security_errors_total
   help: Number of errors preventing normal evaluation. Non-fatal errors may result
     in the latest restricted profile being used for evaluation.

test/instrumentation/documentation/documentation.md

@@ -6,10 +6,10 @@ description: >-
   Details of the metric data that Kubernetes components export.
 ---
 
-## Metrics (v1.26)
+## Metrics (v1.27)
 
-<!-- (auto-generated 2022 Nov 11) -->
+<!-- (auto-generated 2023 Mar 01) -->
-<!-- (auto-generated v1.26) -->
+<!-- (auto-generated v1.27) -->
 This page details the metrics that different Kubernetes components export. You can query the metrics endpoint for these 
 components using an HTTP scrape, and fetch the current metrics data in Prometheus format.
 
@@ -134,6 +134,20 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">completion_mode</div><div class="metric_label">reason</div><div class="metric_label">result</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kube_pod_resource_limit</td>
+<td class="metric_stability_level" data-stability="stable">STABLE</td>
+<td class="metric_type" data-type="custom">Custom</td>
+<td class="metric_description">Resources limit for workloads on the cluster, broken down by pod. This shows the resource usage the scheduler and kubelet expect per pod for resources along with the unit for the resource if any.</td>
+<td class="metric_labels_varying"><div class="metric_label">namespace</div><div class="metric_label">pod</div><div class="metric_label">node</div><div class="metric_label">scheduler</div><div class="metric_label">priority</div><div class="metric_label">resource</div><div class="metric_label">unit</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kube_pod_resource_request</td>
+<td class="metric_stability_level" data-stability="stable">STABLE</td>
+<td class="metric_type" data-type="custom">Custom</td>
+<td class="metric_description">Resources requested by workloads on the cluster, broken down by pod. This shows the resource usage the scheduler and kubelet expect per pod for resources along with the unit for the resource if any.</td>
+<td class="metric_labels_varying"><div class="metric_label">namespace</div><div class="metric_label">pod</div><div class="metric_label">node</div><div class="metric_label">scheduler</div><div class="metric_label">priority</div><div class="metric_label">resource</div><div class="metric_label">unit</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">node_collector_evictions_total</td>
 <td class="metric_stability_level" data-stability="stable">STABLE</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -207,6 +221,25 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 </tbody>
 </table>
 
+### List of Beta Kubernetes Metrics
+
+<table class="table metrics" caption="This is the list of BETA metrics emitted from core Kubernetes components">
+<thead>
+	<tr>
+		<th class="metric_name">Name</th>
+		<th class="metric_stability_level">Stability Level</th>
+		<th class="metric_type">Type</th>
+		<th class="metric_help">Help</th>
+		<th class="metric_labels">Labels</th>
+		<th class="metric_const_labels">Const Labels</th>
+		<th class="metric_deprecated_version">Deprecated Version</th>
+	</tr>
+</thead>
+<tbody>
+
+</tbody>
+</table>
+
 ### List of Alpha Kubernetes Metrics
 
 <table class="table metrics" caption="This is the list of ALPHA metrics emitted from core Kubernetes components">
@@ -345,14 +378,14 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <tr class="metric"><td class="metric_name">apiserver_cel_compilation_duration_seconds</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>
-<td class="metric_description"></td>
+<td class="metric_description">CEL compilation time in seconds.</td>
 <td class="metric_labels_varying"></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">apiserver_cel_evaluation_duration_seconds</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>
-<td class="metric_description"></td>
+<td class="metric_description">CEL evaluation time in seconds.</td>
 <td class="metric_labels_varying"></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
@@ -454,6 +487,41 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">transformation_type</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_envelope_encryption_invalid_key_id_from_status_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of times an invalid keyID is returned by the Status RPC call split by error.</td>
+<td class="metric_labels_varying"><div class="metric_label">error</div><div class="metric_label">provider_name</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_envelope_encryption_key_id_hash_last_timestamp_seconds</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="gauge">Gauge</td>
+<td class="metric_description">The last time in seconds when a keyID was used.</td>
+<td class="metric_labels_varying"><div class="metric_label">key_id_hash</div><div class="metric_label">provider_name</div><div class="metric_label">transformation_type</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_envelope_encryption_key_id_hash_status_last_timestamp_seconds</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="gauge">Gauge</td>
+<td class="metric_description">The last time in seconds when a keyID was returned by the Status RPC call.</td>
+<td class="metric_labels_varying"><div class="metric_label">key_id_hash</div><div class="metric_label">provider_name</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_envelope_encryption_key_id_hash_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of times a keyID is used split by transformation type and provider.</td>
+<td class="metric_labels_varying"><div class="metric_label">key_id_hash</div><div class="metric_label">provider_name</div><div class="metric_label">transformation_type</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_envelope_encryption_kms_operations_latency_seconds</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="histogram">Histogram</td>
+<td class="metric_description">KMS operation duration with gRPC error code status total.</td>
+<td class="metric_labels_varying"><div class="metric_label">grpc_status_code</div><div class="metric_label">method_name</div><div class="metric_label">provider_name</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">apiserver_flowcontrol_current_executing_requests</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="gauge">Gauge</td>
@@ -783,6 +851,13 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">endpoint</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_storage_decode_errors_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of stored object decode errors split by object type</td>
+<td class="metric_labels_varying"><div class="metric_label">resource</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">apiserver_storage_envelope_transformation_cache_misses_total</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -790,6 +865,13 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_storage_events_received_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of etcd events received split by kind.</td>
+<td class="metric_labels_varying"><div class="metric_label">resource</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">apiserver_storage_list_evaluated_objects_total</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -822,7 +904,7 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>
 <td class="metric_description">Latencies in seconds of value transformation operations.</td>
-<td class="metric_labels_varying"><<div class="metric_label">status</div><div class="metric_label">transformation_type</div><div class="metric_label">transformer_prefix</div></td>
+<td class="metric_labels_varying"><div class="metric_label">transformation_type</div><div class="metric_label">transformer_prefix</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">apiserver_storage_transformation_operations_total</td>
@@ -874,6 +956,13 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">resource</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">apiserver_watch_cache_events_received_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Counter of events received in watch cache broken by resource type.</td>
+<td class="metric_labels_varying"><div class="metric_label">resource</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">apiserver_watch_cache_initializations_total</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -1276,8 +1365,8 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <tr class="metric"><td class="metric_name">field_validation_request_duration_seconds</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>
-<td class="metric_description">Response latency distribution in seconds for each field validation value and whether field validation is enabled or not</td>
+<td class="metric_description">Response latency distribution in seconds for each field validation value</td>
-<td class="metric_labels_varying"><div class="metric_label">enabled</div><div class="metric_label">field_validation</div></td>
+<td class="metric_labels_varying"><div class="metric_label">field_validation</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">garbagecollector_controller_resources_sync_error_total</td>
@@ -1343,6 +1432,34 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">cidr</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kube_apiserver_nodeport_allocator_allocated_ports</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="gauge">Gauge</td>
+<td class="metric_description">Gauge measuring the number of allocated NodePorts for Services</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kube_apiserver_nodeport_allocator_allocation_errors_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of errors trying to allocate NodePort</td>
+<td class="metric_labels_varying"><div class="metric_label">scope</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kube_apiserver_nodeport_allocator_allocation_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of NodePort allocations</td>
+<td class="metric_labels_varying"><div class="metric_label">scope</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kube_apiserver_nodeport_allocator_available_ports</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="gauge">Gauge</td>
+<td class="metric_description">Gauge measuring the number of available NodePorts for Services</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">kube_apiserver_pod_logs_pods_logs_backend_tls_failure_total</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -1357,20 +1474,6 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">usage</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
-<tr class="metric"><td class="metric_name">kube_pod_resource_limit</td>
-<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
-<td class="metric_type" data-type="custom">Custom</td>
-<td class="metric_description">Resources limit for workloads on the cluster, broken down by pod. This shows the resource usage the scheduler and kubelet expect per pod for resources along with the unit for the resource if any.</td>
-<td class="metric_labels_varying"><div class="metric_label">namespace</div><div class="metric_label">pod</div><div class="metric_label">node</div><div class="metric_label">scheduler</div><div class="metric_label">priority</div><div class="metric_label">resource</div><div class="metric_label">unit</div></td>
-<td class="metric_labels_constant"></td>
-<td class="metric_deprecated_version"></td></tr>
-<tr class="metric"><td class="metric_name">kube_pod_resource_request</td>
-<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
-<td class="metric_type" data-type="custom">Custom</td>
-<td class="metric_description">Resources requested by workloads on the cluster, broken down by pod. This shows the resource usage the scheduler and kubelet expect per pod for resources along with the unit for the resource if any.</td>
-<td class="metric_labels_varying"><div class="metric_label">namespace</div><div class="metric_label">pod</div><div class="metric_label">node</div><div class="metric_label">scheduler</div><div class="metric_label">priority</div><div class="metric_label">resource</div><div class="metric_label">unit</div></td>
-<td class="metric_labels_constant"></td>
-<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">kubelet_certificate_manager_client_expiration_renew_errors</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -1735,6 +1838,27 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kubelet_topology_manager_admission_duration_ms</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="histogram">Histogram</td>
+<td class="metric_description">Duration in milliseconds to serve a pod admission request.</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kubelet_topology_manager_admission_errors_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">The number of admission request failures where resources could not be aligned.</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">kubelet_topology_manager_admission_requests_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">The number of admission requests where resources have to be aligned.</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">kubelet_volume_metric_collection_duration_seconds</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>
@@ -1931,6 +2055,20 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">zone</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">node_collector_update_all_nodes_health_duration_seconds</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="histogram">Histogram</td>
+<td class="metric_description">Duration in seconds for NodeController to update the health of all nodes.</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">node_collector_update_node_health_duration_seconds</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="histogram">Histogram</td>
+<td class="metric_description">Duration in seconds for NodeController to update the health of a single node.</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">node_collector_zone_health</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="gauge">Gauge</td>
@@ -1980,6 +2118,13 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">clusterCIDR</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">node_ipam_controller_cirdset_max_cidrs</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="gauge">Gauge</td>
+<td class="metric_description">Maximum number of CIDRs that can be allocated.</td>
+<td class="metric_labels_varying"><div class="metric_label">clusterCIDR</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">node_ipam_controller_multicidrset_allocation_tries_per_request</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>
@@ -2008,6 +2153,13 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">clusterCIDR</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">node_ipam_controller_multicirdset_max_cidrs</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="gauge">Gauge</td>
+<td class="metric_description">Maximum number of CIDRs that can be allocated.</td>
+<td class="metric_labels_varying"><div class="metric_label">clusterCIDR</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">node_memory_working_set_bytes</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="custom">Custom</td>
@@ -2134,6 +2286,20 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">resourceclaim_controller_create_attempts_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of ResourceClaims creation requests</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">resourceclaim_controller_create_failures_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of ResourceClaims creation request failures</td>
+<td class="metric_labels_varying"></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">rest_client_exec_plugin_call_total</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="counter">Counter</td>
@@ -2169,6 +2335,13 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 <td class="metric_labels_varying"><div class="metric_label">host</div><div class="metric_label">verb</div></td>
 <td class="metric_labels_constant"></td>
 <td class="metric_deprecated_version"></td></tr>
+<tr class="metric"><td class="metric_name">rest_client_request_retries_total</td>
+<td class="metric_stability_level" data-stability="alpha">ALPHA</td>
+<td class="metric_type" data-type="counter">Counter</td>
+<td class="metric_description">Number of request retries, partitioned by status code, verb, and host.</td>
+<td class="metric_labels_varying"><div class="metric_label">code</div><div class="metric_label">host</div><div class="metric_label">verb</div></td>
+<td class="metric_labels_constant"></td>
+<td class="metric_deprecated_version"></td></tr>
 <tr class="metric"><td class="metric_name">rest_client_request_size_bytes</td>
 <td class="metric_stability_level" data-stability="alpha">ALPHA</td>
 <td class="metric_type" data-type="histogram">Histogram</td>

test/instrumentation/documentation/main.go

@@ -82,6 +82,32 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 </tbody>
 </table>
 
+### List of Beta Kubernetes Metrics
+
+<table class="table metrics" caption="This is the list of BETA metrics emitted from core Kubernetes components">
+<thead>
+	<tr>
+		<th class="metric_name">Name</th>
+		<th class="metric_stability_level">Stability Level</th>
+		<th class="metric_type">Type</th>
+		<th class="metric_help">Help</th>
+		<th class="metric_labels">Labels</th>
+		<th class="metric_const_labels">Const Labels</th>
+		<th class="metric_deprecated_version">Deprecated Version</th>
+	</tr>
+</thead>
+<tbody>
+{{range $index, $metric := .BetaMetrics}}
+<tr class="metric"><td class="metric_name">{{with $metric}}{{.BuildFQName}}{{end}}</td>
+<td class="metric_stability_level" data-stability="{{$metric.StabilityLevel | ToLower}}">{{$metric.StabilityLevel}}</td>
+<td class="metric_type" data-type="{{$metric.Type | ToLower}}">{{$metric.Type}}</td>
+<td class="metric_description">{{$metric.Help}}</td>
+{{if not $metric.Labels }}<td class="metric_labels_varying"></td>{{else }}<td class="metric_labels_varying">{{range $label := $metric.Labels}}<div class="metric_label">{{$label}}</div>{{end}}</td>{{end}}
+{{if not $metric.ConstLabels }}<td class="metric_labels_constant"></td>{{else }}<td class="metric_labels_constant">{{range $key, $value := $metric.ConstLabels}}<div class="metric_label">{{$key}}:{{$value}}</div>{{end}}</td>{{end}}
+{{if not $metric.DeprecatedVersion }}<td class="metric_deprecated_version"></td>{{else }}<td class="metric_deprecated_version">{{$metric.DeprecatedVersion}}</td>{{end}}</tr>{{end}}
+</tbody>
+</table>
+
 ### List of Alpha Kubernetes Metrics
 
 <table class="table metrics" caption="This is the list of ALPHA metrics emitted from core Kubernetes components">
@@ -112,6 +138,7 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu
 
 type templateData struct {
 	AlphaMetrics     []metric
+	BetaMetrics      []metric
 	StableMetrics    []metric
 	GeneratedDate    time.Time
 	GeneratedVersion string
@@ -122,8 +149,8 @@ func main() {
 	var minor string
 	flag.StringVar(&major, "major", "", "k8s major version")
 	flag.StringVar(&minor, "minor", "", "k8s minor version")
-	println(major, minor)
 	flag.Parse()
+	println(major, minor)
 	dat, err := os.ReadFile("test/instrumentation/documentation/documentation-list.yaml")
 	if err == nil {
 		var parsedMetrics []metric
@@ -146,6 +173,7 @@ func main() {
 		sortedMetrics := byStabilityLevel(parsedMetrics)
 		data := templateData{
 			AlphaMetrics:     sortedMetrics["ALPHA"],
+			BetaMetrics:      sortedMetrics["BETA"],
 			StableMetrics:    sortedMetrics["STABLE"],
 			GeneratedDate:    time.Now(),
 			GeneratedVersion: fmt.Sprintf("%v.%v", major, parseMinor(minor)),